Head to head · Assistants reached by message · October 2026 research run

Del vs szn

Del scores 20.6 (F) on agent readiness against szn's 7.3 (F), and leads in 4 of 7 scored categories. Both do assistants reached by message.

Best AI personal assistants that act for one person · All 834 assistants comparisons

DelHuman Interface, Inc. · Platform F20.6/100#991 of 1010 sznNomadic Futures · Platform F7.3/100#1010 of 1010

Which one, for what

Del F

Best for People who want tasks, notes, reminders and Gmail handled by text on the channel they already use.

Ahead on

Reliability, 25 against 5
Payments & pricing, 30 against 20
Maintenance & community, 60 against 2
Transparency & trust, 57 against 23

Also in its favour

Free to start without a card

Watch for

No API, MCP server or A2A endpoint for an outside agent.

szn F

Best for A person who wants calls, emails and bookings done for them and has an access code.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Early access by access code only.

Score by category

Category	Weight this run	Del	szn	Edge
Reliability	16%20	25	5	Del +20
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	10	10	even
Agent ergonomics	13%16.2	0	0	even
Security & auth	14%17.5	0	0	even
Payments & pricing	10%12.5	30	20	Del +10
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	60	2	Del +58
Transparency & trust	7%8.8	57	23	Del +34
Negative events	≤15	0	0
Total		F 20.6/100	F 7.3/100

Facts side by side

Fact	Del	szn
Kind	Platform	Platform
Vendor	Human Interface, Inc.	Nomadic Futures
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	OAuth or key	OAuth or key
Pricing	Paid	Free
x402	no	no
Licence	Closed service under Del's Terms of Service (Human Interface, Inc., a Delaware corporation, last updated 5 August 2026).	Closed service. No terms of service were found on theszn.ai. A privacy policy and an acceptable use policy (both last updated March 2026) apply.
Read-only variant documented	no	yes
llms.txt	yes	yes
Last release	2026-10-07	none
Terms last updated		no document linked
Privacy policy last updated
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver

Verdicts

Del

Del is a hosted texting assistant and task workspace across iMessage, WhatsApp, Telegram, SMS, Discord and Slack, with a near-daily public changelog and a card-free 14-day trial. No outside agent can call it, no status page or security contact was found, and recent updates let some email actions skip approval.

szn

szn is an errand assistant in early access that makes calls, sends emails and books for its owner, free during the preview for people with an access code. No outside agent can call it, no terms of service or legal entity appear in its policies, and its privacy policy says nothing on training.

Before you call either

Del

Don't plan to call Del from another agent. It answers only the owner's messaging threads and web workspace.
Tell the owner web browsing tasks are limited to five a month on Standard and unlimited on Pro.

szn

Don't plan to call szn from another agent. It answers only its web app, iMessage, SMS and email for the owner.
Tell the owner they need an access code to start, and that the acceptable use policy makes them responsible for confirming actions.

Questions

Which is better for AI agents, Del or szn?

Del scores 20.6 (F) on agent readiness against szn's 7.3 (F), and leads in 4 of 7 scored categories.

Other comparisons with Del or szn

Disclosure

Del competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

szn competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

Machine-readable

This page as Markdown /compare/del-vs-szn.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/del.json · /api/v1/tools/szn.json
From a terminal anchor compare del szn (the CLI)
Over MCP compare_tools {"a": "del", "b": "szn"} at /mcp, no key